Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1224 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.9964. Min Range: -11.9964
Max Act: 11.9964. Min Act: -0.1700
Data Index: 2265055 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.9964. Min Range: -11.9964
Max Act: 11.8089. Min Act: -0.1700
Data Index: 5338771 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.9964. Min Range: -11.9964
Max Act: 11.6214. Min Act: -0.1700
Data Index: 6743767 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.9964. Min Range: -11.9964
Max Act: 11.3714. Min Act: -0.1700
Data Index: 8485269 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.9964. Min Range: -11.9964
Max Act: 11.3089. Min Act: -0.1700
Data Index: 1771283 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.9964. Min Range: -11.9964
Max Act: 11.3089. Min Act: -0.1700
Data Index: 2415175 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.9964. Min Range: -11.9964
Max Act: 11.3089. Min Act: -0.1700
Data Index: 4644906 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.9964. Min Range: -11.9964
Max Act: 11.2464. Min Act: -0.1700
Data Index: 7324367 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.9964. Min Range: -11.9964
Max Act: 11.2464. Min Act: -0.1700
Data Index: 4086095 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.9964. Min Range: -11.9964
Max Act: 11.2464. Min Act: -0.1700
Data Index: 7501168 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.9964. Min Range: -11.9964
Max Act: 11.2464. Min Act: -0.1700
Data Index: 201400 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.9964. Min Range: -11.9964
Max Act: 11.2464. Min Act: -0.1700
Data Index: 4796768 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.9964. Min Range: -11.9964
Max Act: 11.1214. Min Act: -0.1700
Data Index: 5133693 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.9964. Min Range: -11.9964
Max Act: 11.1839. Min Act: -0.1700
Data Index: 4846963 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.9964. Min Range: -11.9964
Max Act: 11.1839. Min Act: -0.1700
Data Index: 318065 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.9964. Min Range: -11.9964
Max Act: 11.1839. Min Act: -0.1700
Data Index: 5482023 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.9964. Min Range: -11.9964
Max Act: 11.1214. Min Act: -0.1700
Data Index: 8814883 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.9964. Min Range: -11.9964
Max Act: 11.0589. Min Act: -0.1700
Data Index: 2912587 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.9964. Min Range: -11.9964
Max Act: 11.0589. Min Act: -0.1700
Data Index: 2091689 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.9964. Min Range: -11.9964
Max Act: 10.9964. Min Act: -0.1700
Data Index: 2176838 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19